Enhancing Security and Privacy in Cloud – Based Healthcare Data Through Machine Learning DOI
Aasheesh Shukla, Hemant Singh Pokhariya, Jacob J. Michaelson

et al.

Published: Dec. 29, 2023

It is becoming more and important for healthcare providers to protect the integrity security of sensitive medical data as they use cloud computing processing storage. This work explores field machine learning algorithms that are secure privacy-preserving when applied information in environments. We investigate sophisticated cryptography, federated learning, differentiating privacy techniques using an interpretive philosophy a method based on deduction. Our results highlight computational expense associated with cryptographic protocols, while also revealing their nuanced performance potential enabling calculations. Federated shown be effective collaborative model training, providing workable approach analysis over-dispersed datasets. Differential systems require careful parameter calibration because demonstrate delicate balance between value preservation.

Language: Английский

SCOF: Security-Aware Computation Offloading Using Federated Reinforcement Learning in Industrial Internet of Things With Edge Computing DOI
Kai Peng, Peiyun Xiao, Shangguang Wang

et al.

IEEE Transactions on Services Computing, Journal Year: 2024, Volume and Issue: 17(4), P. 1780 - 1792

Published: March 19, 2024

Industry 5.0 facilitates the intelligent upgrade of smart factories in Industrial Internet Things (IIoT), and also introduces a plethora data processing challenges. Mobile edge computing offloads to servers for processing, easing pressure reducing system cost. However, contain numerous sensitive information, offloading them directly may pose risk leakage. To address these challenges, we investigate localedge collaborative factory system. Specifically, firstly model tasks as directed acyclic graph, formulate problem Markov decision process, considering optimization latency, energy consumption number overtime tasks. Then, propose security-aware computation method using federated reinforcement learning IIoT, named SCOF. SCOF employs learning, keeping local uploading parameters aggregation. The transmission passes through an artificial noise channel protect against eavesdropping. Meanwhile, utilizes differential privacy security deep selecting near-optimal decisions. Finally, abundant experiments are conducted under real dataset. results show that has better perfomance than state-of-the-art baseline algorithms.

Language: Английский

Citations

8
An efficient task offloading and auto-scaling approach for IoT applications in edge computing environment DOI

Milad Ghahari-Bidgoli,

Mostafa Ghobaei‐Arani, Ahmad Sharif

et al.

Computing, Journal Year: 2025, Volume and Issue: 107(5)

Published: May 1, 2025

Language: Английский

Citations

0
Federated Deep Q-network: A Dynamic Task Allocation Strategy for UAV-Assisted Cell-Free Networks DOI

Jian He,

Chunyu Pan,

Jincheng Wang

et al.

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 451 - 459

Published: Jan. 1, 2025

Language: Английский

Citations

0
UAV-Driven Task Offloading and Wireless Power Transfer: A Fusion of Lyapunov Optimization and Reinforcement Learning in Edge Computing DOI
Xianhao Shen, Jing Nie,

Ling Gu

et al.

Physical Communication, Journal Year: 2025, Volume and Issue: unknown, P. 102719 - 102719

Published: May 1, 2025

Language: Английский

Citations

0
FeDRL-D2D: Federated Deep Reinforcement Learning- Empowered Resource Allocation Scheme for Energy Efficiency Maximization in D2D-Assisted 6G Networks DOI Creative Commons
Hafiz Muhammad Fahad Noman, Kaharudin Dimyati, Kamarul Ariffin Noordin

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 109775 - 109792

Published: Jan. 1, 2024

Device-to-device (D2D)-assisted 6G networks are expected to support the proliferation of ubiquitous mobile applications by enhancing system capacity and overall energy efficiency towards a connected-sustainable world. However, stringent quality service (QoS) requirements for ultra-massive connectivity, limited network resources, interference management significant challenges deploying multiple device-to-device pairs (DDPs) without disrupting cellular users. Hence, intelligent resource power control indispensable alleviating among DDPs optimize performance global efficiency. Considering this, we present Federated DRL-based method energy-efficient in D2D-assisted heterogeneous (HetNet). We formulate joint optimization problem channel allocation maximize system's under QoS constraints user equipment (CUEs) DDPs. The proposed scheme employs federated learning decentralized training paradigm address privacy, double-deep Q-network (DDQN) is used management. DDQN uses two separate Q-networks action selection target estimation rationalize transmit dynamic which as agents could reuse uplink channels CUEs. Simulation results depict that improves 41.52% achieves better sum rate 11.65%, 24.78%, 47.29% than multi-agent actor-critic (MAAC), distributed deep-deterministic policy gradient (D3PG), deep Q (DQN) scheduling, respectively. Moreover, 5.88%, 15.79%, 27.27% reduction outage probability compared MAAC, D3PG, DQN respectively, makes it robust solution networks.

Language: Английский

Citations

2
Distributed Deep Reinforcement Learning for Autonomous Iot Healthcare Devices in the Cloud DOI
Aasheesh Shukla, Hemant Singh Pokhariya, Jacob J. Michaelson

et al.

Published: Dec. 29, 2023

The ethical and philosophical problems concerning the cooperation of AI systems human artists are also examined in this study. In addressing authorship, agency, very essence creation, changing position as co-creators with intelligent algorithms is explored. It looks at how can question change conventional ideas creative competence. Additionally, study into affects promotion distribution art. AI-driven marketing tactics provide improved targeting customers, personalized experiences, optimal promotional efforts by utilizing insights based on data predictive analytics. focuses these developments transform relationships between galleries their patrons, ultimately fostering a more varied inclusive art scene. system's potential many healthcare scenarios has been validated through simulations practical experiments, which have received excellent feedback from providers. A critical review emphasizes need to address deployment issues security concerns, while highlighting exciting convergence IoT devices DDRL. paper ends suggestions for research, significance issues, user interface improvements, real-world validation. Through smooth integration DDRL-enhanced Internet Things (IoT) medical equipment clinical practice, our research eventually improves patient care transforms delivery healthcare.

Language: Английский

Citations

1
A DRL-based online real-time task scheduling method with ISSA strategy DOI

Zhikuan Zhu,

Hao Xu,

Yingyu He

et al.

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(6), P. 8207 - 8223

Published: April 8, 2024

Language: Английский

Citations

0
Application Research of Edge Computing in Airborne Networks Algorithm DOI

Chuxin Li,

Jin Xiao

Lecture notes in electrical engineering, Journal Year: 2024, Volume and Issue: unknown, P. 448 - 457

Published: Jan. 1, 2024

Language: Английский

Citations

0
Joint Optimization of Resource Allocation and Topology Formation for Hierarchical Federated Learning in Smart Grids DOI

Hossein Savadkoohian,

Ha Minh Nguyen, Kim Khoa Nguyen

et al.

GLOBECOM 2022 - 2022 IEEE Global Communications Conference, Journal Year: 2024, Volume and Issue: unknown, P. 1593 - 1598

Published: Dec. 8, 2024

Language: Английский

Citations

0
Enhancing Security and Privacy in Cloud – Based Healthcare Data Through Machine Learning DOI
Aasheesh Shukla, Hemant Singh Pokhariya, Jacob J. Michaelson

et al.

Published: Dec. 29, 2023

It is becoming more and important for healthcare providers to protect the integrity security of sensitive medical data as they use cloud computing processing storage. This work explores field machine learning algorithms that are secure privacy-preserving when applied information in environments. We investigate sophisticated cryptography, federated learning, differentiating privacy techniques using an interpretive philosophy a method based on deduction. Our results highlight computational expense associated with cryptographic protocols, while also revealing their nuanced performance potential enabling calculations. Federated shown be effective collaborative model training, providing workable approach analysis over-dispersed datasets. Differential systems require careful parameter calibration because demonstrate delicate balance between value preservation.

Language: Английский

Citations

0